© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 20015
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports teams and their performance or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charging
    -0.15
     Charging
    -0.15
     nackte
    -0.15
    Portland
    -0.15
    ikan
    -0.15
    IPA
    -0.14
    ento
    -0.14
     Portland
    -0.14
    ainted
    -0.14
    NV
    -0.14
    POSITIVE LOGITS
     Jets
    0.40
     Jet
    0.37
    Jets
    0.36
     jets
    0.35
     jet
    0.34
    jets
    0.31
    Jet
    0.31
     Gang
    0.30
    jet
    0.27
     NY
    0.24
    Activations Density 0.012%

    No Known Activations